On 07/05/19 10:43 PM, Mahesh J Salgaonkar wrote:
On 2019-04-16 16:06:13 Tue, Hari Bathini wrote:
OPAL loads kernel & initrd at 512MB offset (256MB size), also exported
as ibm,opal/dump/fw-load-area. So, if boot memory size of FADump is
less than 768MB, kernel memory to be exported as '/proc/vmcore' would
be overwritten by f/w while loading kernel & initrd. To avoid such a
scenario, enforce a minimum boot memory size of 768MB on OPAL platform.

Also, skip using FADump if a newer F/W version loads kernel & initrd
above 768MB.

Signed-off-by: Hari Bathini <hbath...@linux.ibm.com>
---
  arch/powerpc/kernel/fadump-common.h          |   15 +++++++++++++--
  arch/powerpc/kernel/fadump.c                 |    8 ++++++++
  arch/powerpc/platforms/powernv/opal-fadump.c |   23 +++++++++++++++++++++++
  3 files changed, 44 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/kernel/fadump-common.h 
b/arch/powerpc/kernel/fadump-common.h
index 1bd3aeb..f59fdc7 100644
--- a/arch/powerpc/kernel/fadump-common.h
+++ b/arch/powerpc/kernel/fadump-common.h
@@ -24,14 +24,25 @@
  #define RMA_END               (ppc64_rma_size)
/*
+ * With kernel & initrd loaded at 512MB (with 256MB size), enforce a minimum
+ * boot memory size of 768MB to ensure f/w loading kernel and initrd doesn't
+ * mess with crash'ed kernel's memory during MPIPL.
+ */
+#define OPAL_MIN_BOOT_MEM      (0x30000000UL)
+
+/*
   * On some Power systems where RMO is 128MB, it still requires minimum of
   * 256MB for kernel to boot successfully. When kdump infrastructure is
   * configured to save vmcore over network, we run into OOM issue while
   * loading modules related to network setup. Hence we need additional 64M
   * of memory to avoid OOM issue.
   */
-#define MIN_BOOT_MEM   (((RMA_END < (0x1UL << 28)) ? (0x1UL << 28) : RMA_END) \
-                       + (0x1UL << 26))
+#define PSERIES_MIN_BOOT_MEM   (((RMA_END < (0x1UL << 28)) ? (0x1UL << 28) : \
+                                RMA_END) + (0x1UL << 26))
+
+#define MIN_BOOT_MEM   ((fw_dump.fadump_platform ==                    \
+                        FADUMP_PLATFORM_POWERNV) ? OPAL_MIN_BOOT_MEM : \
+                        PSERIES_MIN_BOOT_MEM)
Can we hide this behind fadump_ops.get_bootmem_min() instead of common code
doing platform check ?

/* The upper limit percentage for user specified boot memory size (25%) */
  #define MAX_BOOT_MEM_RATIO                    4
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index ba26169..3c3adc2 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -582,6 +582,14 @@ int __init fadump_reserve_mem(void)
                                ALIGN(fw_dump.boot_memory_size,
                                                        FADUMP_CMA_ALIGNMENT);
  #endif
+
+               if ((fw_dump.fadump_platform == FADUMP_PLATFORM_POWERNV) &&
+                   (fw_dump.boot_memory_size < OPAL_MIN_BOOT_MEM)) {
and here too.. fadump_ops.validate_bootmem_size() ? push platform specific
stuff behind fadump_ops.

Actually, it would be fine to make this check for both platforms.
So, fadump_ops.get_bootmem_min() callback can be used at both places, I guess..

- Hari

Reply via email to